Evolutionary Robotics: The Biology,Intelligence,and Technology

By Stefano Nolfi, Dario Floreano. 2000

679 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4e4138efcc9f30ec08daf5564bb2c38f866f51f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Please Scroll down for Article Connection Science Developmental Robotics: a Survey Developmental Robotics: a Survey (2003, unknown): “In general, autonomous and self-organized formation of spatiotemporal patterns is a distinguishing trait of ‘open nonequilibrium systems’, that is, of systems in which ‘energy’ ﬂows: (a) from one region of the system to another (the system is not at equilibrium); and (b) in and out of the system…”
The interaction of maturational constraints and intrinsic motivations in active motor development (2011, unknown): “Other kinds of techniques, for example ones based on natural actor-critic architectures in model based reinforcement learning [24] or coming from evolutionary robotics [25], could also be used.”
Creating Brain-Like Intelligence (2009, background): “The field of evolutionary robots [ 32 ] demonstrates this.”
A Survey on Information and Communication Technologies for Industry 4.0: State-of-the-Art, Taxonomies, Perspectives, and Challenges (2019, methodology): “Evolutionary robotics is a technique for the automatic creation of autonomous robots that leverages the tools of neural networks, genetic algorithms, and dynamic systems [130].”
Embodied Evolution: Distributing an evolutionary algorithm in a population of robots (2002, background): “Finally, Section 8 outlines some caveats regarding our approach, followed by conclusions in Section 9.”
Imitation Learning (2017, methodology): “Evolutionary algorithms (EAs) are popular optimization methods that have extensively been used to ﬁnd motor trajectories for robotic tasks [Nolﬁ and Floreano 2000].”
Self-Organization, Embodiment, and Biologically Inspired Robotics (2007, background): “In evolutionary robotics, the most widespread approach is to start with a fixed morphology and evolve the robot controller, typically a neural network ( 44 ).”
Levels of dynamics and adaptive behavior in evolutionary neural controllers (2002, background): “In the great majority of experiments in Evolutionary Robotics ( Nol and Floreano, 2000 ) evolved control systems consist of articial neural networks most of which include recurrent connections.”
Preparing for the Unknown: Learning a Universal Policy with Online System Identification (2017, background): “The discrepancy between what can be achieved in simulation and that in real world is referred as the “Reality Gap” in the Evolutionary Robotics community [22, 14].”
Self-Organized Coordinated Motion in Groups of Physically Connected Robots (2007, methodology): “It is worth noting that this behavior was obtained through an automatic design methodology, that is, artificial evolution, which is particularly tailored for the synthesis of self-organizing behaviors [15], [21].”
Evolution of Plastic Control Networks (2001, methodology): “Evolutionary Robotics (Cliff et al., 1993; Nolfi and Floreano, 2000 ) implies the use of a population, but in most cases only one physical robot is used to test the performance of each individual in the population one after the other.”
Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots (2001, background): “A population of 60 individuals is evolved using rank-based truncated selection, one-point crossover, bit mutation, and elitism [ 18 ].”